Mandarin phonetic recognition using mixture hidden Markov models with time duration function

Author

Bao, Lixin ; Toyama, Jun ; Shimbo, Masaru

Author_Institution

Div. of Syst. & Inf. Eng., Hokkaido Univ., Sapporo, Japan

fYear

1998

fDate

1998

Firstpage

621

Abstract

This paper proposes mixture hidden Markov models (HMM) with a time duration function to solve the recognition of Mandarin Chinese diphthongs and several words that resemble diphthongs. We propose an autoregression model to represent the dynamical relationships of observation symbols with time variance. The model can improve the weaknesses of standard HMM and nonstationary HMM

Keywords

autoregressive processes; hidden Markov models; speech recognition; HMM; Mandarin Chinese; autoregression model; diphthongs; mixture hidden Markov models; observation symbols; phonetic recognition; time duration function; time variance; Decoding; Hidden Markov models; Loudspeakers; Natural languages; Polynomials; Speech analysis; Speech recognition; Statistical analysis; Systems engineering and theory; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-4325-5

Type

conf

DOI

10.1109/ICOSP.1998.770288

Filename

770288

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=339149